Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2376 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2291. Min Range: -4.2291
Max Act: 4.2291. Min Act: -0.1700
Data Index: 1908261 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2291. Min Range: -4.2291
Max Act: 4.0104. Min Act: -0.1700
Data Index: 2136860 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.8853. Min Act: -0.1700
Data Index: 1065228 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.8853. Min Act: -0.1700
Data Index: 4612741 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.8540. Min Act: -0.1700
Data Index: 6227812 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.8384. Min Act: -0.1700
Data Index: 1920275 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.8384. Min Act: -0.1700
Data Index: 8517224 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.7446. Min Act: -0.1700
Data Index: 1162203 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.6976. Min Act: -0.1700
Data Index: 6335383 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.6820. Min Act: -0.1700
Data Index: 8553822 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.6820. Min Act: -0.1700
Data Index: 8009915 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.6664. Min Act: -0.1700
Data Index: 6916224 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.6507. Min Act: -0.1700
Data Index: 2793306 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.6351. Min Act: -0.1700
Data Index: 1065229 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.6351. Min Act: -0.1700
Data Index: 1028576 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.6194. Min Act: -0.1700
Data Index: 3811954 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.6038. Min Act: -0.1700
Data Index: 1724648 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.5881. Min Act: -0.1700
Data Index: 2880076 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.5725. Min Act: -0.1700
Data Index: 8493642 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2291. Min Range: -4.2291
Max Act: 3.5725. Min Act: -0.1700
Data Index: 4910968 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19